From: tip-bot for Peter Zijlstra <a.p.zijlstra@chello.nl>
To: linux-tip-commits@vger.kernel.org
Cc: linux-kernel@vger.kernel.org, eranian@google.com, hpa@zytor.com,
mingo@redhat.com, arjan@linux.intel.com, a.p.zijlstra@chello.nl,
tglx@linutronix.de, mingo@elte.hu
Subject: [tip:perf/core] perf_events, x86: Implement Intel Westmere support
Date: Fri, 29 Jan 2010 09:30:25 GMT [thread overview]
Message-ID: <tip-452a339a976e7f782c786eb3f73080401e2fa3a6@git.kernel.org> (raw)
In-Reply-To: <20100127221122.151865645@chello.nl>
Commit-ID: 452a339a976e7f782c786eb3f73080401e2fa3a6
Gitweb: http://git.kernel.org/tip/452a339a976e7f782c786eb3f73080401e2fa3a6
Author: Peter Zijlstra <a.p.zijlstra@chello.nl>
AuthorDate: Wed, 27 Jan 2010 23:07:48 +0100
Committer: Ingo Molnar <mingo@elte.hu>
CommitDate: Fri, 29 Jan 2010 09:01:48 +0100
perf_events, x86: Implement Intel Westmere support
The new Intel documentation includes Westmere arch specific
event maps that are significantly different from the Nehalem
ones. Add support for this generation.
Found the CPUID model numbers on wikipedia.
Also ammend some Nehalem constraints, spotted those when looking
for the differences between Nehalem and Westmere.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arjan van de Ven <arjan@linux.intel.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Stephane Eranian <eranian@google.com>
LKML-Reference: <20100127221122.151865645@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
arch/x86/kernel/cpu/perf_event.c | 124 +++++++++++++++++++++++++++++++++++--
1 files changed, 117 insertions(+), 7 deletions(-)
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index cf10839..3fac0bf 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -244,18 +244,26 @@ static struct event_constraint intel_core_event_constraints[] =
static struct event_constraint intel_nehalem_event_constraints[] =
{
- FIXED_EVENT_CONSTRAINT(0xc0, (0x3|(1ULL<<32))), /* INSTRUCTIONS_RETIRED */
- FIXED_EVENT_CONSTRAINT(0x3c, (0x3|(1ULL<<33))), /* UNHALTED_CORE_CYCLES */
+ FIXED_EVENT_CONSTRAINT(0xc0, (0xf|(1ULL<<32))), /* INSTRUCTIONS_RETIRED */
+ FIXED_EVENT_CONSTRAINT(0x3c, (0xf|(1ULL<<33))), /* UNHALTED_CORE_CYCLES */
INTEL_EVENT_CONSTRAINT(0x40, 0x3), /* L1D_CACHE_LD */
INTEL_EVENT_CONSTRAINT(0x41, 0x3), /* L1D_CACHE_ST */
INTEL_EVENT_CONSTRAINT(0x42, 0x3), /* L1D_CACHE_LOCK */
INTEL_EVENT_CONSTRAINT(0x43, 0x3), /* L1D_ALL_REF */
+ INTEL_EVENT_CONSTRAINT(0x48, 0x3), /* L1D_PEND_MISS */
INTEL_EVENT_CONSTRAINT(0x4e, 0x3), /* L1D_PREFETCH */
- INTEL_EVENT_CONSTRAINT(0x4c, 0x3), /* LOAD_HIT_PRE */
INTEL_EVENT_CONSTRAINT(0x51, 0x3), /* L1D */
- INTEL_EVENT_CONSTRAINT(0x52, 0x3), /* L1D_CACHE_PREFETCH_LOCK_FB_HIT */
- INTEL_EVENT_CONSTRAINT(0x53, 0x3), /* L1D_CACHE_LOCK_FB_HIT */
- INTEL_EVENT_CONSTRAINT(0xc5, 0x3), /* CACHE_LOCK_CYCLES */
+ INTEL_EVENT_CONSTRAINT(0x63, 0x3), /* CACHE_LOCK_CYCLES */
+ EVENT_CONSTRAINT_END
+};
+
+static struct event_constraint intel_westmere_event_constraints[] =
+{
+ FIXED_EVENT_CONSTRAINT(0xc0, (0xf|(1ULL<<32))), /* INSTRUCTIONS_RETIRED */
+ FIXED_EVENT_CONSTRAINT(0x3c, (0xf|(1ULL<<33))), /* UNHALTED_CORE_CYCLES */
+ INTEL_EVENT_CONSTRAINT(0x51, 0x3), /* L1D */
+ INTEL_EVENT_CONSTRAINT(0x60, 0x1), /* OFFCORE_REQUESTS_OUTSTANDING */
+ INTEL_EVENT_CONSTRAINT(0x63, 0x3), /* CACHE_LOCK_CYCLES */
EVENT_CONSTRAINT_END
};
@@ -286,6 +294,97 @@ static u64 __read_mostly hw_cache_event_ids
[PERF_COUNT_HW_CACHE_OP_MAX]
[PERF_COUNT_HW_CACHE_RESULT_MAX];
+static __initconst u64 westmere_hw_cache_event_ids
+ [PERF_COUNT_HW_CACHE_MAX]
+ [PERF_COUNT_HW_CACHE_OP_MAX]
+ [PERF_COUNT_HW_CACHE_RESULT_MAX] =
+{
+ [ C(L1D) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = 0x010b, /* MEM_INST_RETIRED.LOADS */
+ [ C(RESULT_MISS) ] = 0x0151, /* L1D.REPL */
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = 0x020b, /* MEM_INST_RETURED.STORES */
+ [ C(RESULT_MISS) ] = 0x0251, /* L1D.M_REPL */
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = 0x014e, /* L1D_PREFETCH.REQUESTS */
+ [ C(RESULT_MISS) ] = 0x024e, /* L1D_PREFETCH.MISS */
+ },
+ },
+ [ C(L1I ) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = 0x0380, /* L1I.READS */
+ [ C(RESULT_MISS) ] = 0x0280, /* L1I.MISSES */
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = 0x0,
+ [ C(RESULT_MISS) ] = 0x0,
+ },
+ },
+ [ C(LL ) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = 0x0324, /* L2_RQSTS.LOADS */
+ [ C(RESULT_MISS) ] = 0x0224, /* L2_RQSTS.LD_MISS */
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = 0x0c24, /* L2_RQSTS.RFOS */
+ [ C(RESULT_MISS) ] = 0x0824, /* L2_RQSTS.RFO_MISS */
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = 0x4f2e, /* LLC Reference */
+ [ C(RESULT_MISS) ] = 0x412e, /* LLC Misses */
+ },
+ },
+ [ C(DTLB) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = 0x010b, /* MEM_INST_RETIRED.LOADS */
+ [ C(RESULT_MISS) ] = 0x0108, /* DTLB_LOAD_MISSES.ANY */
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = 0x020b, /* MEM_INST_RETURED.STORES */
+ [ C(RESULT_MISS) ] = 0x010c, /* MEM_STORE_RETIRED.DTLB_MISS */
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = 0x0,
+ [ C(RESULT_MISS) ] = 0x0,
+ },
+ },
+ [ C(ITLB) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = 0x01c0, /* INST_RETIRED.ANY_P */
+ [ C(RESULT_MISS) ] = 0x0185, /* ITLB_MISSES.ANY */
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ },
+ [ C(BPU ) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = 0x00c4, /* BR_INST_RETIRED.ALL_BRANCHES */
+ [ C(RESULT_MISS) ] = 0x03e8, /* BPU_CLEARS.ANY */
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ },
+};
+
static __initconst u64 nehalem_hw_cache_event_ids
[PERF_COUNT_HW_CACHE_MAX]
[PERF_COUNT_HW_CACHE_OP_MAX]
@@ -2423,7 +2522,9 @@ static __init int intel_pmu_init(void)
x86_pmu.event_constraints = intel_core_event_constraints;
pr_cont("Core2 events, ");
break;
- case 26:
+
+ case 26: /* 45 nm nehalem, "Bloomfield" */
+ case 30: /* 45 nm nehalem, "Lynnfield" */
memcpy(hw_cache_event_ids, nehalem_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
@@ -2437,6 +2538,15 @@ static __init int intel_pmu_init(void)
x86_pmu.event_constraints = intel_gen_event_constraints;
pr_cont("Atom events, ");
break;
+
+ case 37: /* 32 nm nehalem, "Clarkdale" */
+ case 44: /* 32 nm nehalem, "Gulftown" */
+ memcpy(hw_cache_event_ids, westmere_hw_cache_event_ids,
+ sizeof(hw_cache_event_ids));
+
+ x86_pmu.event_constraints = intel_westmere_event_constraints;
+ pr_cont("Westmere events, ");
+ break;
default:
/*
* default constraints for v2 and up
next prev parent reply other threads:[~2010-01-29 9:31 UTC|newest]
Thread overview: 12+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-01-27 22:07 [PATCH 0/4] perf x86 fixes Peter Zijlstra
2010-01-27 22:07 ` [PATCH 1/4] perf_events: x86: Fix event constraint masks Peter Zijlstra
2010-01-29 9:29 ` [tip:perf/core] perf_events, " tip-bot for Peter Zijlstra
2010-01-27 22:07 ` [PATCH 2/4] perf_events: x86: Clean up hw_perf_*_all() implementation Peter Zijlstra
2010-01-29 9:30 ` [tip:perf/core] perf_events, " tip-bot for Peter Zijlstra
2010-01-27 22:07 ` [PATCH 3/4] perf_events: x86: Implement westmere support Peter Zijlstra
2010-01-29 9:30 ` tip-bot for Peter Zijlstra [this message]
2010-01-27 22:07 ` [PATCH 4/4] perf_events: x86: Remove spurious counter reset from x86_pmu_enable() Peter Zijlstra
2010-01-29 9:30 ` [tip:perf/core] perf_events, " tip-bot for Peter Zijlstra
2010-01-29 7:55 ` [PATCH 0/4] perf x86 fixes Ingo Molnar
2010-01-29 8:04 ` [PATCH 5/4] perf_events: Fix sample_period transfer on inherit Peter Zijlstra
2010-01-29 9:30 ` [tip:perf/core] " tip-bot for Peter Zijlstra
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=tip-452a339a976e7f782c786eb3f73080401e2fa3a6@git.kernel.org \
--to=a.p.zijlstra@chello.nl \
--cc=arjan@linux.intel.com \
--cc=eranian@google.com \
--cc=hpa@zytor.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-tip-commits@vger.kernel.org \
--cc=mingo@elte.hu \
--cc=mingo@redhat.com \
--cc=tglx@linutronix.de \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.